CN115497306A - Speed interval weight calculation method based on GIS data - Google Patents
Speed interval weight calculation method based on GIS data Download PDFInfo
- Publication number
- CN115497306A CN115497306A CN202211462775.1A CN202211462775A CN115497306A CN 115497306 A CN115497306 A CN 115497306A CN 202211462775 A CN202211462775 A CN 202211462775A CN 115497306 A CN115497306 A CN 115497306A
- Authority
- CN
- China
- Prior art keywords
- road
- speed
- traffic flow
- data
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 claims description 34
- 150000001875 compounds Chemical class 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 238000011835 investigation Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000000556 factor analysis Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 241001420287 Strobilanthes maculata Species 0.000 claims description 4
- 230000033228 biological regulation Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000007417 hierarchical cluster analysis Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims 1
- 238000012827 research and development Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000013028 emission testing Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a speed interval weight calculation method based on GIS data, which comprises the following steps: s1, selecting a typical city; s2, classifying the road traffic conditions of the typical city in the step S1; s3, collecting road traffic flow data and calculating characteristics; s4, establishing a multi-dimensional traffic flow model and verifying; s5, calculating urban traffic flow characteristics based on the multi-dimensional traffic flow model; and S6, calculating a weight factor. The invention has the beneficial effects that: GIS data is innovatively introduced to evaluate the actual running condition of the vehicle, a multi-dimensional traffic flow model is constructed based on video traffic flow data, and weight factors of all speed intervals can be objectively calculated, so that the working condition of the vehicle is closer to the actual running state of the vehicle. To sum up, this patent can provide technical support for government and enterprise's policy making, product research and development in the automobile operating mode relevant field.
Description
Technical Field
The invention belongs to the field of transportation, and particularly relates to a speed interval weight calculation method based on GIS data.
Background
Automotive conditions are the standard for vehicle energy consumption/emission testing in the automotive industry. In the construction of the working condition, the authenticity and the accuracy of the working condition are influenced by the weight of three speed intervals, namely low speed, medium speed and high speed. The traditional speed interval threshold value confirmation method is mainly based on fleet data acquisition for calculation, and weight deviation is easily caused when the number of the fleet and route planning are unreasonable. Quantification of operating condition weights is a common problem in the industry.
With the development of a geographic information system, GIS vehicle travel data provides a good basis for quantifying the working condition weight by using a big data method by virtue of the advantages of wide road coverage, strong real-time performance and low acquisition cost. However, the acquired GIS big data information only includes basic information such as Vehicle speed, position and time, the traffic information of the road cannot be directly obtained, and the calculation of Vehicle Hours (VHT) and Vehicle travel distance (VKT) cannot be realized.
The invention is characterized in that video traffic flow data is utilized and various traffic flow influence factors are comprehensively considered, a multi-dimensional traffic flow model is established, and a speed interval weight factor calculation method based on GIS data is provided.
Disclosure of Invention
In view of the above, the present invention aims to provide a speed interval weight calculation method based on GIS data, so as to solve the problem that the traditional working condition weight is greatly influenced by fleet selection, and the present invention utilizes GIS traffic big data capable of objectively reflecting the real driving situation of the vehicles in China, A traffic flow model suitable for typical cities across the country is established, a GIS data-based traffic flow calculation method is provided, accurate calculation of national speed interval weight is achieved, and a data basis is provided for working condition development.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a speed interval weight calculation method based on GIS data comprises the following steps:
s1, selecting a typical city;
s2, classifying the road traffic conditions of the typical city in the step S1;
s3, respectively carrying out road traffic flow data acquisition and feature calculation aiming at various road traffic conditions in the step S2;
s4, establishing a multi-dimensional traffic flow model and verifying based on the road traffic flow data collected in the step S3;
s5, calculating travel time distribution characteristics of the urban transportation vehicles based on the multi-dimensional traffic flow model established in the step S4;
s6, calculating weight factors of all speed intervals based on the vehicle travel time distribution characteristics in the step S5;
the selection of a typical city in step S1 includes the steps of:
a1, counting indexes of 663 cities in the country, wherein the indexes comprise GDP, population number, per-capita automobile holding capacity, urban road area and vehicle per-capita road area;
a2, performing factor analysis on the indexes counted in the step A1 to obtain representative factors in the indexes; a3, performing hierarchical clustering analysis according to the representative factors in the step A2, and dividing cities into different categories;
and A4, selecting typical cities from the various cities in the step A3 according to the vehicle holding amount proportion.
Further, the road traffic flow data collection and feature calculation in step S3 includes the following steps:
b1, selecting typical city investigation roads in each type of road traffic conditions;
b2, carrying out traffic flow data acquisition on the typical urban investigation road in the step B1 to obtain road investigation data of each type of road traffic condition;
and B3, calculating the road average speed, the road flow and the road density of each type of road traffic condition according to the road investigation data in the step B2, and taking the road average speed, the road flow and the road density of each type of road traffic condition as the road traffic flow characteristics of each type of road traffic condition.
Further, the calculation formula of the road average speed is as follows:
in the formula (I), the compound is shown in the specification,is the average speed of the link and is,ldetecting a road segment length for the video;the average travel time for the vehicle i to pass through the detection area,as vehiclesiThe average velocity across the detection zone.
Further, the calculation formula of the road density is as follows:
in the formula (I), the compound is shown in the specification,in order to be the density of the road,in order to be the traffic of the road,is the link average speed.
Further, the establishing and verifying of the multi-dimensional traffic flow model in step S4 includes the following steps:
c1, preprocessing the road traffic flow characteristics of each type of road traffic condition in the step B3 to remove abnormal data, and randomly separating the road traffic flow characteristics of each type of road traffic condition after preprocessing according to the proportion of 3:1 to obtain training set data and test set data of each type of road traffic condition; the training set data is speed-density data and the test set data is speed-flow data.
C2, establishing a multi-dimensional traffic flow model according to the training set data and the test set data in the step C1;
and C3, carrying out precision verification on the multi-dimensional traffic flow model established in the step C2 through the test set data.
Further, the multi-dimensional traffic flow model building in step C2 includes the following steps:
c21, according to the traffic conditions of each type of road in the step S2, performing Underwood, greenshields and Van aerode traffic flow model fitting on the basis of training set data respectively, and selecting a correlation coefficient R by using a least square method 2 An optimal model; if the correlation coefficient of the road traffic condition is the same as that of the road traffic condition<0.7, then enter step C22 and then enter step C3; whether or notDirectly entering the step C3;
and C22, dividing the training set data of each type of road traffic condition entering the step into three parts of free flow, synchronous flow and blocked flow according to the speed standard deviation under each road density, and fitting by using traffic flow models of Underwood, greenshiels and Van aerode respectively to establish a multi-dimensional traffic flow model.
Further, the calculating of the urban traffic flow characteristic in step S5 includes the steps of:
d1, removing GIS road abnormal data by using a road average speed reasonable threshold formula, judging whether the road speed loss rate of the processed GIS road data is less than 30%, if so, performing road speed supplement by using an ARIMA model, and entering the step D2; if not, the speed loss rate is more than 30%, the GIS road data is not processed, and the step D2 is carried out;
d2, calculating the average number of lanes and the length of each road, and matching the road id with the road running speed to obtain a GIS road-speed database;
d3, calculating the GIS road-speed database in the step D2 by using the multi-dimensional traffic flow model to obtain the flow and VHT of all roads of the whole road network at different moments.
Further, the reasonable threshold formula of the road average speed is as follows:
in the formula (I), the compound is shown in the specification,representing road limit values, whose values are determined by traffic regulations and road indications,in order to be the speed of the road vehicle,the value is 1 to 1.3 for the correction coefficient.
Further, the calculation formula of the road average lane number is as follows:
in the formula (I), the compound is shown in the specification,the average number of lanes of the road is,for the length of the section i to be,is the number of lanes for road segment i.
Further, the calculation of the weighting factor of each speed interval in step S6 includes the following steps:
e1, dividing a threshold value according to a speed interval, and dividing a low-speed interval, a medium-speed interval and a high-speed interval respectively;
e2, calculating the accumulated vehicle hours of a low-speed interval, a medium-speed interval and a high-speed interval through a weight factor calculation formula to obtain weight factors of all speed intervals of each city;
the weight factor calculation formula is as follows:
in the formula (I), the compound is shown in the specification,is as followsiThe weight factor of each speed interval is,the number of cities is the number of cities,is as followsjThe first cityiThe cumulative number of vehicle hours for each speed interval,is as followsjThe cumulative number of vehicle hours for each city.
Compared with the prior art, the speed interval weight calculation method based on the GIS data has the following advantages that:
according to the speed interval weight calculation method based on the GIS data, the GIS data is innovatively introduced to evaluate the actual running condition of the vehicle, the multi-dimensional traffic flow model is constructed based on the video traffic flow data, and the weight factors of each speed interval can be objectively calculated, so that the working condition of the vehicle is closer to the actual running state of the vehicle. To sum up, this patent can provide technical support for government and enterprise's policy making, product research and development in the automobile operating mode relevant field.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flow chart illustrating details of obtaining a weighting factor of a speed interval according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of selecting a traffic flow model according to an embodiment of the present invention;
FIG. 3 is a schematic view of road traffic flow at various levels according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a distribution of road segment speeds-VHT of each level according to an embodiment of the present invention;
fig. 5 is a schematic overall flow chart of the method according to the embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The noun interpretation:
the main component method comprises the following steps: is one of the factor analysis. Few important principal components are standardized as common factors. The principal component model and the common factor model are considered to be different in the early stage of factor analysis, and the principal component estimation of the common factor model is proposed in hammen in 1967. The principal component method is a special case of the principal axis factor method.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
The method of the present invention will be described in further detail with reference to the accompanying drawings, in which fig. 1 is a detailed flow of speed interval weight calculation based on GIS data, and fig. 5 is an overall flow of speed interval weight calculation based on GIS data.
A speed interval weight calculation method based on GIS data comprises the following steps:
s1, selecting a typical city;
s2, classifying the road traffic conditions of the typical city in the step S1;
s3, respectively carrying out road traffic flow data acquisition and feature calculation aiming at various road traffic conditions in the step S2;
s4, establishing a multi-dimensional traffic flow model and verifying based on the road traffic flow data collected in the step S3;
s5, calculating travel time distribution characteristics of the urban transportation vehicles based on the multi-dimensional traffic flow model established in the step S4;
and S6, calculating weight factors of all speed intervals based on the vehicle travel time distribution characteristics in the step S5.
The invention innovatively introduces GIS data to evaluate the actual running condition of the vehicle, constructs a multi-dimensional traffic flow model based on video traffic flow data, and can objectively calculate the weight factor of each speed interval, so that the automobile working condition is closer to the actual running state of the vehicle. To sum up, this patent can provide technical support for government and enterprise's policy making, product research and development in the automobile operating mode relevant field.
In a preferred embodiment of the present invention, the selecting of the representative city in step S1 comprises the following steps:
a1, counting indexes of 663 cities in the country, wherein the indexes comprise GDP, population number, per-capita automobile holding capacity, urban road area and vehicle per-capita road area;
a2, performing factor analysis on the indexes counted in the step A1 to obtain representative factors in the indexes; a3, performing hierarchical clustering analysis according to the representative factors in the step A2, and dividing cities into different categories;
and A4, selecting typical cities from the various cities in the step A3 according to the vehicle holding amount proportion.
In this example, 1. City selection:
and (3) carrying out statistics on 663 total urban GDP, per capita automobile holding quantity, per automobile road area, urban road area and other 10 indexes in the whole country except for the stations of Gao and Australia, carrying out factor analysis on the 10 indexes, and calculating 10 index correlation coefficient matrixes and KMO (Kernel-based expert inspection). The calculation result shows that the correlation coefficient between the variables is generally higher, and factor analysis can be carried out.
Calculating a factor load matrix by using a principal component method, and extracting a common factor according to the following two rules: (1) a factor for variance (eigenvalue) greater than 0; and (2) the common factor accumulated variance contribution rate reaches 85%. Finally 2 common factors are obtained by extraction.
By rotating the factor load matrix, it can be found that for a common factor of 1, the load of variable factors such as the population of the permanent residence, the GDP, the road area of the city at the end of the year and the like is obviously higher. For the common factor 2, the load of variable factors such as the holding capacity of the people-average automobile and the road area of the automobile-average is obviously high. The common factor 1 reflects the scales of GDP, vehicles and roads, the factor 2 reflects the condition of the vehicle holding per person and the condition of the road area per vehicle, the common factor 1 is defined as an index of city scale, and the common factor 2 is defined as an index of vehicle road level.
The factor analysis model is a linear combination with original variables as common factors, and obtains an expression of the common factors by using a regression method, thereby calculating and obtaining the score of each city factor. And carrying out hierarchical clustering analysis on the cities according to the factor scores, and clustering the cities into 5 types.
Next, a city sample is taken. According to the 5-category results, the urban vehicle holding amount, the region and the terrain characteristics are combined, and finally 41 cities are selected.
2. Road traffic condition classification
The traffic flow of different road types, travel time and time periods shows different change rules under the influence of road use difference and travel requirements. According to the results of resident household investigation, the ratio of the commuting trip to the total trip quantity is the highest. During holidays, the commuting demand of residents is reduced, and the difference between the traffic condition and the working day is large. To ensure the accuracy of the traffic flow model, road traffic conditions are classified into 80 categories according to cities (5 categories), road grades (4 categories), workdays/holidays and daytime/nights.
Regarding the traffic model classification types, the present invention proposes to include cities (5 types), road classes (4 types), workdays/holidays, daytime/nighttime.
And (3) in the aspect of model calculation: the method comprises the steps of classifying road conditions, determining models and parameters, enabling different road traffic flow models to be consistent under the same condition, not changing along with the change of parameters such as the number of lanes and the like, and then calculating uniformly.
In a preferred embodiment of the present invention, the collecting of the road traffic flow data and the feature calculating in step S3 includes the steps of:
b1, selecting typical urban investigation roads in each type of road traffic condition;
b2, carrying out traffic flow data acquisition on the typical urban investigation road in the step B1 to obtain road investigation data of each type of road traffic condition;
and B3, calculating the road average speed, the road flow and the road density of each type of road traffic condition according to the road investigation data in the step B2, and taking the road average speed, the road flow and the road density of each type of road traffic condition as the road traffic flow characteristics of each type of road traffic condition.
In a preferred embodiment of the present invention, the calculation formula of the road average speed is:
in the formula (I), the compound is shown in the specification,is the average speed of the link and is,ldetecting a road segment length for the video;the average travel time for the vehicle i to pass through the detection area,as vehiclesiBy the average speed of the detection area.
In a preferred embodiment of the present invention, the calculation formula of the road density is:
in the formula (I), the compound is shown in the specification,in order to be the density of the road,in order to be the traffic of the road,is the link average speed.
In this embodiment, 3. Traffic flow data acquisition and feature calculation
(1) Urban investigation road selection: and selecting a road with urban road service level representativeness and road geometrical characteristic representativeness as a traffic flow model investigation road. The service level refers to a quality index of a road traffic flow operation condition experienced by a driver, and is generally represented by indexes such as average running speed, driving freedom, traffic delay and the like; the road geometry conditions are generally indexes such as lane number, lane width and road length;
the screening principle of the traffic flow model investigation road is that the significance of selecting typical cities is the same, and the typical road needs to be selected because all data cannot be collected.
(2) Collecting traffic flow data: and shooting and selecting a road monitoring video, counting the speed and time points of all vehicles passing through the detection area, wherein the instantaneous speed of a part of vehicles is far beyond the speed limit value of the corresponding collected road, and performing maximum processing on the speed limit value of the numerical value. The speed threshold value calculation formula is a road speed limit value multiplied by 1.2, and as a speed abnormal threshold value, a speed point exceeding the threshold value is given as the threshold value. Wherein the purpose of maximization is to cull out inappropriate data.
(3) Calculating road traffic flow characteristics: and calculating traffic flow data such as road flow, road average speed, road density and the like through the speed and time point of the vehicle passing through the detection area for modeling a subsequent traffic flow model. The calculation purpose is to obtain road traffic flow data for subsequent traffic flow modeling.
Specifically, (1) urban research road selection
Based on the urban traffic flow model classification, a typical city is selected in each type of city, roads of four road grades including an expressway, a trunk road and a secondary branch road are selected in each typical city, 4 roads are selected in each grade of road, and the collection time comprises working days and holiday days.
In order to ensure that the investigated roads are representative, corresponding roads are selected according to the service level (road congestion index, average driving speed and the like) of urban roads, the road geometry (the number of road lanes, the road length and the like) and other indexes. When the section of a road is selected for investigation, the road is selected to be flat and straight, the section has a certain distance from an intersection, and the influence of road conditions, signal lamps and the like on the speed of a vehicle is reduced.
(2) Traffic flow data collection
And erecting a camera on the selected road section to shoot a road monitoring video. And counting the speed and time point when all vehicles pass through the detection area.
(3) Road traffic flow feature calculation
Road traffic flow characteristics require statistics of road average speed, road flow and road density. The road flow is the number of passing vehicles in a unit time period.
The road average speed may be calculated from the speed of the vehicle through the road segment in the area, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,is the average speed of the link and is,ldetecting a road segment length for the video;the average travel time for the vehicle i to pass through the detection area,as vehiclesiBy the average speed of the detection area.
Wherein, the instantaneous speed of part of vehicles far exceeds the speed limit value of the road, and the value is processed to the maximum of the speed limit value. The speed threshold value calculation formula is the road speed limit value multiplied by 1.2, and as the speed abnormal threshold value, the speed point exceeding the threshold value is given as the threshold value.
Road density is an important parameter in a multi-dimensional traffic flow model that describes the state of a road. The calculation formula is as follows.
In the formula (I), the compound is shown in the specification,in order to be the density of the road,in order to be the traffic of the road,is the link average speed.
The road traffic flow characteristic calculation results are shown in table 1.
TABLE 1 road traffic flow characteristics
In a preferred embodiment of the present invention, the establishing of the multidimensional traffic flow model and the verification in the step S4 comprises the following steps:
c1, preprocessing the road traffic flow characteristics of each type of road traffic condition in the step B3 to remove abnormal data, and randomly separating the road traffic flow characteristics of each type of road traffic condition after preprocessing according to the proportion of 3:1 to obtain training set data and test set data of each type of road traffic condition; wherein the training set data is speed-density data and the test set data is speed-flow data.
C2, establishing a multi-dimensional traffic flow model according to the training set data and the test set data in the step C1;
and C3, carrying out precision verification on the multi-dimensional traffic flow model established in the step C2 through the test set data.
In a preferred embodiment of the present invention, the multi-dimensional traffic flow model building in step C2 includes the steps of:
c21, according to the traffic conditions of each type of road in the step S2, performing Underwood, greenshields and Van aerode traffic flow model fitting on the basis of training set data respectively, and selecting a correlation coefficient R by using a least square method 2 An optimal model; if the correlation coefficient of the road traffic condition is the same as that of the road traffic condition<0.7, then enter step C22 and then enter step C3; if not, directly entering the step C3;
and C22, dividing the training set data of each type of road traffic condition entering the step into three parts of free flow, synchronous flow and blocked flow according to the speed standard deviation under each road density, and respectively fitting by using an Underwood, greenshiels and Van aerode traffic flow model to establish a multi-dimensional traffic flow model.
In this embodiment, 4. Multidimensional traffic flow model selection and verification
(1) Preprocessing road traffic flow characteristics: the method is used for removing road traffic flow characteristic abnormal data, and aims to better represent a model and divide a traffic flow data set into a training set and a testing set.
(2) Selecting a multi-dimensional traffic flow model: in order to ensure that the model is more consistent with the accuracy of the actual road condition, according to the traffic condition classification obtained in the step 2, underwood, greenshiels and Van aerode traffic flow model fitting is respectively carried out on the basis of the speed-density data of the training set, and a correlation coefficient R is selected by utilizing a least square method 2 And (5) optimizing the model. If the road condition under the condition of partial urban traffic is more complex, the correlation coefficient R of a single road 2 And if the density is lower, dividing the speed-density data into three parts of free flow, synchronous flow and blocked flow according to the speed standard deviation under each density, fitting the segmented models, and finally establishing a multi-dimensional traffic flow model covering multiple working conditions.
(3) And (3) multi-dimensional traffic flow model verification: and based on the multidimensional traffic flow model, calculating the traffic flow by using the average speed of the roads in the test set, comparing the traffic flow with the road flow data in the test set, and verifying the accuracy of the multidimensional traffic flow model by using the relative error and the absolute error of the traffic flow in each hour as model indexes.
In particular, multidimensional traffic flow model selection and verification
(1) Road traffic flow characteristic preprocessing
In the data acquisition process, the speed of the acquired vehicles is influenced by emergencies such as crossing of roads by pedestrians, traffic accidents, road maintenance and the like, and when the original data are analyzed, the change rule of a research object can be covered by the abnormal data and important influence is generated on the analysis result, so that the original data need to be preprocessed to ensure the reliability of the original data.
Based on the collected road traffic flow characteristics, dividing density intervals by taking traffic flow density as a horizontal axis, drawing box line graphs for speed distribution in each density interval, and searching and eliminating abnormal values by using a box line graph principle.
Three road traffic data collected from various cities and roads of various levels are randomly selected as a training set, and the remaining one road traffic data is used as a test set.
(2) Multi-dimensional traffic flow model selection
And respectively performing model fitting according to the classification of the traffic modes and the model classification. The number of vehicles at night is small, the road state is mainly in a free flow state, the correlation between the flow and the speed is small, and the traffic flow mainly changes along with time, so that a time-flow cubic equation is selected for fitting. Model fitting is shown in fig. 2 (a).
As the number of cars on a road increases, the density increases, the inter-vehicle distance becomes smaller, and the inter-vehicle interaction causes the driver to reduce the speed of the vehicle, and thus the speed decreases with the increase in density. Based on the traffic flow basic relational expression, the flow can be calculated according to the density and the vehicle speed.
Based on city classification and road traffic classification, respectively based on training set speed-density numberFitting the traffic flow models of Greenshields, underwood and Van aerode according to the correlation coefficient R 2 The optimal model is selected and fitted as shown in fig. 2 (b) (c) (d).
If the road condition under partial urban traffic conditions is more complex, the correlation coefficient R of the single model 2 And if the traffic flow is lower, performing sectional fitting on the traffic flow. When the traffic density is small, the interaction between the vehicles is small, the speed fluctuation on the road is large, the interaction between the vehicles is large along with the increase of the density, and the speeds of the vehicles on the road tend to be consistent. Based on the research on the actual traffic flow data, the speed standard deviation of the vehicles under different traffic states and the traffic flow density is found to be greatly different. Therefore, the point at which the standard deviation of the speed greatly changes at each density is used as the critical density for dividing the traffic flow state. Dividing the traffic flow state into three parts of free flow, synchronous flow and blocking flow, carrying out traffic flow model fitting in a segmentation mode, selecting an optimal model, and obtaining a fitting result shown in table 2.
TABLE 2 traffic flow model fitting results
And further establishing a multi-dimensional traffic flow model base for distinguishing city categories, road grades, working days/holidays and daytime/night traffic conditions based on the model fitting conditions.
(3) Traffic flow model validation
And carrying out traffic flow calculation by utilizing the speed of the test set based on the multi-dimensional traffic flow model, comparing the traffic flow calculation with traffic flow test set flow data, and taking the relative error of the traffic flow in each hour of the test set speed and the traffic flow test set flow data as a model index for verifying the accuracy of the traffic flow model, wherein the model is considered to be accurate when the relative error is less than 10%.
In a preferred embodiment of the present invention, the calculating of the urban traffic flow characteristic in step S5 includes the steps of:
d1, removing GIS road abnormal data by using a road average speed reasonable threshold formula, judging whether the road speed loss rate of the processed GIS road data is less than 30%, if so, performing road speed supplement by using an ARIMA model, and entering the step D2; if not, the speed loss rate is more than 30%, the GIS road data is not processed, and the step D2 is carried out;
d2, calculating the average number of lanes and the length of each road, and matching the road id with the road running speed to obtain a GIS road-speed database;
d3, calculating the GIS road-speed database in the step D2 by using the multi-dimensional traffic flow model to obtain the flow and VHT of all roads of the whole road network at different moments.
In a preferred embodiment of the present invention, the reasonable threshold formula of the road average speed is:
in the formula (I), the compound is shown in the specification,the representative road limit value is determined by traffic regulations and road indications,in order to be the speed of the road vehicle,the value is 1 to 1.3 for the correction coefficient.
In a preferred embodiment of the present invention, the calculation formula of the road average lane number is:
in the formula (I), the compound is shown in the specification,the average number of lanes of the road is,for the length of the section i,Is the number of lanes for road segment i.
In this embodiment, 5. Urban traffic flow characteristic calculation
(1) Preprocessing GIS data: due to GPS drift, network transmission and the like, the data can be outlier, missing and the like. And setting a speed threshold value for outliers with overlarge (undersize) data to eliminate the outliers. Calculating the loss rate of the GIS data of each road, and supplementing the speed data with the loss rate below 30% by using a differential Integrated Moving Average autoregressive model (ARIMA).
(2) And (3) road information matching: and calculating road information such as the average number of lanes and the length of the road, and matching the road id with the road running speed to obtain a GIS road-speed database.
(3) Calculating the flow of the whole road network: and calculating the GIS road-speed database by using the calibrated multi-dimensional traffic flow model to obtain the flow and VHT of all roads of the whole road network at different moments.
Specifically, urban traffic flow characteristic calculation
(1) GIS data preprocessing
GIS data is as the actual data of traveling of vehicle, and because reasons such as GPS drift, network transmission, data can have the condition such as data anomaly, disappearance. Missing data refers to blank data that has not been collected for some reason, and appears as no data. The abnormal data is mainly caused by abnormal GPS or sudden change of collected data due to environment, which causes the data to be abnormally too large or too small.
The velocity anomaly value identifies anomalous data by thresholding the data. For the road average speed traffic speed, the reasonable threshold formula is:
in the formula (I), the compound is shown in the specification,the representative road limit value is comprehensively determined by traffic regulations and road instructions,in order to be the speed of the road vehicle,the value is 1 to 1.3 for the correction coefficient.
Calculating the loss rate of the road GIS traffic data, if the loss rate of the road speed is less than 30%, and supplementing the road speed by using an ARIMA model; the speed loss rate is more than 30%, and the road data is not processed.
(2) GIS speed information and road information matching
The number of the partial roads is changed, but the GIS road speed data is the average speed of the whole road every 5 minutes, so the average number of the roads is calculated to obtain the flow information of the whole road section, and the formula is as follows:
in the formula (I), the compound is shown in the specification,the average number of lanes of the road is,for the length of the section i to be,the number of lanes of the road section i;
and matching the GIS speed information and the road information one by using the road names to construct a GIS road-speed database.
(3) Traffic flow model calculation
And taking the GIS road-speed database as input, and calculating by using a multi-dimensional traffic flow model library to obtain the road traffic flow. The calculation results are shown in fig. 3.
In order to calculate the weighting factor of each speed interval, the vehicle travel time (VHT) in each speed interval needs to be counted. The calculation formula is as follows:
in the formula (I), the compound is shown in the specification,the number of vehicle hours for the road i,the traffic flow of the road i is shown,the average travel time of the vehicle on a certain road i,for the length of the road i the road length,is the link i average speed.
The VHT values corresponding to the speed intervals are respectively counted to obtain a speed-VHT distribution, and the result is shown in fig. 4.
In a preferred embodiment of the present invention, the calculation of the weighting factor for each speed interval in step S6 includes the steps of:
e1, dividing threshold values according to speed intervals, and dividing a low-speed interval, a medium-speed interval and a high-speed interval respectively;
e2, calculating the accumulated vehicle hours of a low-speed interval, a medium-speed interval and a high-speed interval through a weight factor calculation formula to obtain weight factors of all speed intervals of each city;
the weight factor calculation formula is as follows:
in the formula (I), the compound is shown in the specification,is a firstiThe weight factor of each speed interval is determined,the number of cities is the number of cities,is as followsjSecond cityiThe cumulative number of vehicle hours for each speed interval,is as followsjThe cumulative number of vehicle hours for each city.
In this embodiment, 6. Weight factor calculation
And dividing a low-speed section, a medium-speed section and a high-speed section according to the speed section division threshold value, further calculating the accumulated vehicle hours of the low-speed section, the medium-speed section and the high-speed section, and finally obtaining the weight factor of each speed section of each city.
The weight of each speed interval in the whole country can be obtained by dividing the accumulated vehicle hours of different speed intervals of each city by the total vehicle hours of each speed interval. The calculation formula is as follows:
in the formula (I), the compound is shown in the specification,is as followsiThe weight factor of each speed interval is determined,the number of cities is the number of cities,is as followsjThe first cityiCumulative vehicle for individual speed intervalThe number of hours,is a firstjThe cumulative vehicle hours for each city, the results of which are shown in table 3.
TABLE 3 speed Interval weighting factor
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A speed interval weight calculation method based on GIS data is characterized in that: the method comprises the following steps:
s1, selecting a typical city;
s2, classifying the road traffic conditions of the typical city in the step S1;
s3, respectively carrying out road traffic flow data acquisition and feature calculation aiming at various road traffic conditions in the step S2;
s4, establishing a multi-dimensional traffic flow model and verifying based on the road traffic flow data collected in the step S3;
s5, calculating travel time distribution characteristics of the urban traffic vehicles based on the multi-dimensional traffic flow model established in the step S4;
s6, calculating weight factors of all speed intervals based on the vehicle travel time distribution characteristics in the step S5;
the selection of a typical city in step S1 comprises the following steps:
a1, counting indexes of 663 cities in the country, wherein the indexes comprise GDP, population number, number of people holding automobiles per capita, urban road area and vehicle road area per capita;
a2, performing factor analysis on the indexes counted in the step A1 to obtain representative factors in the indexes; a3, performing hierarchical clustering analysis according to the representative factors in the step A2, and dividing cities into different categories;
and A4, selecting typical cities from the various cities in the step A3 according to the vehicle holding amount proportion.
2. The method for calculating the speed interval weight based on the GIS data according to claim 1, wherein the method comprises the following steps: the road traffic flow data collection and feature calculation in step S3 includes the steps of:
b1, selecting typical urban investigation roads in each type of road traffic condition;
b2, carrying out traffic flow data acquisition on the typical urban investigation road in the step B1 to obtain road investigation data of each type of road traffic condition;
and B3, calculating the road average speed, the road flow and the road density of each type of road traffic condition according to the road investigation data in the step B2, and taking the road average speed, the road flow and the road density of each type of road traffic condition as the road traffic flow characteristics of each type of road traffic condition.
3. The method for calculating the speed interval weight based on the GIS data according to claim 2, wherein the method comprises the following steps: the calculation formula of the road average speed is as follows:
4. The method for calculating the speed interval weight based on the GIS data according to claim 2, wherein the method comprises the following steps: the calculation formula of the road density is as follows:
5. The method for calculating the speed interval weight based on the GIS data according to claim 2, wherein the method comprises the following steps: the establishment of the multidimensional traffic flow model and the verification in the step S4 comprise the following steps:
c1, preprocessing the road traffic flow characteristics of each type of road traffic condition in the step B3 to obtain training set data and test set data of each type of road traffic condition;
c2, establishing a multi-dimensional traffic flow model according to the training set data and the test set data in the step C1;
and C3, carrying out precision verification on the multi-dimensional traffic flow model established in the step C2 through the test set data.
6. The method for calculating the speed interval weight based on the GIS data according to claim 5, wherein the method comprises the following steps: the multi-dimensional traffic flow model establishment in the step C2 comprises the following steps:
c21, according to each type of road traffic conditions in the step S2, respectivelyPerforming Underwood, greenshields and Van aerode traffic flow model fitting based on training set data, and selecting a correlation coefficient R by using a least square method 2 An optimal model; if the correlation coefficient of the road traffic condition is the same as that of the road traffic condition<0.7, then enter step C22 and then enter step C3; if not, directly entering the step C3;
and C22, dividing the training set data of each type of road traffic condition entering the step into three parts of free flow, synchronous flow and blocked flow according to the speed standard deviation under each road density, and fitting by using traffic flow models of Underwood, greenshiels and Van aerode respectively to establish a multi-dimensional traffic flow model.
7. The method for calculating the speed interval weight based on the GIS data according to claim 6, wherein the method comprises the following steps: the calculation of the urban traffic flow characteristic in step S5 includes the steps of:
d1, removing GIS road abnormal data by using a road average speed reasonable threshold formula, judging whether the road speed loss rate of the processed GIS road data is less than 30%, if so, performing road speed supplement by using an ARIMA model, and entering the step D2; if not, the speed loss rate is more than 30%, the GIS road data is not processed, and the step D2 is carried out;
d2, calculating the average number of lanes and the average length of the roads, and matching the road id with the road running speed to obtain a GIS road-speed database;
d3, calculating the GIS road-speed database in the step D2 by using the multi-dimensional traffic flow model to obtain the flow and VHT of all roads of the whole road network at different moments.
8. The method for calculating the speed interval weight based on the GIS data according to claim 7, wherein the method comprises the following steps: the reasonable threshold formula of the road average speed is as follows:
9. The method for calculating the speed interval weight based on the GIS data according to claim 7, wherein: the calculation formula of the average number of the lanes of the road is as follows:
10. The method for calculating the speed interval weight based on the GIS data according to claim 1, wherein the method comprises the following steps: the calculation of each speed interval weight factor in step S6 includes the steps of:
e1, dividing a threshold value according to a speed interval, and dividing a low-speed interval, a medium-speed interval and a high-speed interval respectively;
e2, calculating the accumulated vehicle hours of a low-speed interval, a medium-speed interval and a high-speed interval through a weight factor calculation formula to obtain weight factors of all speed intervals of each city;
the weight factor calculation formula is:
in the formula (I), the compound is shown in the specification,is as followsiThe weight factor of each speed interval is,the number of cities is the number of cities,is as followsjThe first cityiThe cumulative number of vehicle hours for each speed interval,is as followsjCumulative vehicle hours for each city.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211462775.1A CN115497306A (en) | 2022-11-22 | 2022-11-22 | Speed interval weight calculation method based on GIS data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211462775.1A CN115497306A (en) | 2022-11-22 | 2022-11-22 | Speed interval weight calculation method based on GIS data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115497306A true CN115497306A (en) | 2022-12-20 |
Family
ID=85115447
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211462775.1A Pending CN115497306A (en) | 2022-11-22 | 2022-11-22 | Speed interval weight calculation method based on GIS data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115497306A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116756205A (en) * | 2023-05-12 | 2023-09-15 | 北京建筑大学 | Driving cycle-oriented subdivision speed VKT and VHT distribution construction method |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102819955A (en) * | 2012-09-06 | 2012-12-12 | 北京交通发展研究中心 | Road network operation evaluation method based on vehicle travel data |
CN104778834A (en) * | 2015-01-23 | 2015-07-15 | 哈尔滨工业大学 | Urban road traffic jam judging method based on vehicle GPS data |
CN107067722A (en) * | 2017-04-24 | 2017-08-18 | 中国汽车技术研究中心 | Novel vehicle running condition construction method |
CN108171975A (en) * | 2017-12-29 | 2018-06-15 | 吉林大学 | A kind of city automobile speed of service Forecasting Methodology being distributed based on section and intersection |
CN108470444A (en) * | 2018-03-21 | 2018-08-31 | 特斯联(北京)科技有限公司 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
CN108492553A (en) * | 2018-03-12 | 2018-09-04 | 中山大学 | A kind of movable vehicle horizontal analysis method towards real-time road network emission evaluation |
CN108629974A (en) * | 2018-05-17 | 2018-10-09 | 电子科技大学 | Take the traffic circulation index method for building up of urban road traffic network feature into account |
CN109932191A (en) * | 2019-03-15 | 2019-06-25 | 中国汽车技术研究中心有限公司 | A kind of real road driving cycle library and construction method |
CN110009908A (en) * | 2019-03-27 | 2019-07-12 | 招商局重庆交通科研设计院有限公司 | The traffic route length control method calculated based on road traffic control time and region |
CN111275983A (en) * | 2020-02-14 | 2020-06-12 | 北京百度网讯科技有限公司 | Vehicle tracking method, device, electronic equipment and computer-readable storage medium |
CN112562311A (en) * | 2020-10-21 | 2021-03-26 | 中国汽车技术研究中心有限公司 | Method and device for obtaining working condition weight factor based on GIS big data |
CN113744530A (en) * | 2021-09-08 | 2021-12-03 | 河南科技大学 | Construction method of vehicle working condition |
CN114136312A (en) * | 2021-11-25 | 2022-03-04 | 中汽研汽车检验中心(天津)有限公司 | Gradient speed combined working condition development device and development method |
CN114791975A (en) * | 2021-01-25 | 2022-07-26 | 中国科学院计算技术研究所临沂分所(临沂中科人工智能创新研究院) | Cross-platform AI model recommendation system and method |
CN114923711A (en) * | 2022-05-31 | 2022-08-19 | 东风汽车集团股份有限公司 | RDE simulation test method, device, equipment and readable storage medium |
CN115293585A (en) * | 2022-08-09 | 2022-11-04 | 广东旭诚科技有限公司 | Method for building road network motor vehicle dynamic emission list based on GIS-T |
-
2022
- 2022-11-22 CN CN202211462775.1A patent/CN115497306A/en active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102819955A (en) * | 2012-09-06 | 2012-12-12 | 北京交通发展研究中心 | Road network operation evaluation method based on vehicle travel data |
CN104778834A (en) * | 2015-01-23 | 2015-07-15 | 哈尔滨工业大学 | Urban road traffic jam judging method based on vehicle GPS data |
CN107067722A (en) * | 2017-04-24 | 2017-08-18 | 中国汽车技术研究中心 | Novel vehicle running condition construction method |
CN108171975A (en) * | 2017-12-29 | 2018-06-15 | 吉林大学 | A kind of city automobile speed of service Forecasting Methodology being distributed based on section and intersection |
CN108492553A (en) * | 2018-03-12 | 2018-09-04 | 中山大学 | A kind of movable vehicle horizontal analysis method towards real-time road network emission evaluation |
CN108470444A (en) * | 2018-03-21 | 2018-08-31 | 特斯联(北京)科技有限公司 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
CN108629974A (en) * | 2018-05-17 | 2018-10-09 | 电子科技大学 | Take the traffic circulation index method for building up of urban road traffic network feature into account |
WO2020187100A1 (en) * | 2019-03-15 | 2020-09-24 | 中国汽车技术研究中心有限公司 | Actual road driving cycle database and construction method |
CN109932191A (en) * | 2019-03-15 | 2019-06-25 | 中国汽车技术研究中心有限公司 | A kind of real road driving cycle library and construction method |
CN110009908A (en) * | 2019-03-27 | 2019-07-12 | 招商局重庆交通科研设计院有限公司 | The traffic route length control method calculated based on road traffic control time and region |
CN111275983A (en) * | 2020-02-14 | 2020-06-12 | 北京百度网讯科技有限公司 | Vehicle tracking method, device, electronic equipment and computer-readable storage medium |
CN112562311A (en) * | 2020-10-21 | 2021-03-26 | 中国汽车技术研究中心有限公司 | Method and device for obtaining working condition weight factor based on GIS big data |
CN114791975A (en) * | 2021-01-25 | 2022-07-26 | 中国科学院计算技术研究所临沂分所(临沂中科人工智能创新研究院) | Cross-platform AI model recommendation system and method |
CN113744530A (en) * | 2021-09-08 | 2021-12-03 | 河南科技大学 | Construction method of vehicle working condition |
CN114136312A (en) * | 2021-11-25 | 2022-03-04 | 中汽研汽车检验中心(天津)有限公司 | Gradient speed combined working condition development device and development method |
CN114923711A (en) * | 2022-05-31 | 2022-08-19 | 东风汽车集团股份有限公司 | RDE simulation test method, device, equipment and readable storage medium |
CN115293585A (en) * | 2022-08-09 | 2022-11-04 | 广东旭诚科技有限公司 | Method for building road network motor vehicle dynamic emission list based on GIS-T |
Non-Patent Citations (3)
Title |
---|
刘昱: "中国乘用车工况构建", 《交通运输系统工程与信息》 * |
尹月华等: "基于GIS的北京市道路交通流特性研究", 《公路工程》 * |
陆化普 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116756205A (en) * | 2023-05-12 | 2023-09-15 | 北京建筑大学 | Driving cycle-oriented subdivision speed VKT and VHT distribution construction method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107067722B (en) | Method for constructing vehicle running condition | |
CN104809878B (en) | Method for detecting abnormal condition of urban road traffic by utilizing GPS (Global Positioning System) data of public buses | |
CN109147330B (en) | Congestion identification method and device | |
CN111310786B (en) | Traffic detector abnormality diagnosis method and device based on random forest classifier | |
CN110276953A (en) | Rule-breaking vehicle travel risk analysis method based on BEI-DOU position system | |
CN110363985B (en) | Traffic data analysis method, device, storage medium and equipment | |
CN110807919A (en) | Urban road network traffic operation situation evaluation method based on vehicle passing data | |
CN111242484B (en) | Vehicle risk comprehensive evaluation method based on transition probability | |
CN112053558A (en) | Traffic jam state identification method, device and equipment | |
CN109191861B (en) | System and method for detecting abnormal behavior of fee evasion vehicle on expressway based on video detector | |
CN114783183A (en) | Monitoring method and system based on traffic situation algorithm | |
CN105355049A (en) | Highway running state evaluation method based on macroscopic fundamental diagram | |
CN102087789B (en) | System and method for discriminating traffic conditions based on traffic conditions parameter | |
CN115691120A (en) | Congestion identification method and system based on highway running water data | |
CN114819305B (en) | Path planning method based on carbon emission measurement scale | |
CN106056903A (en) | Method for detecting road congestion areas based on GPS (Global Positioning System) data | |
Biswas et al. | Assessment of level-of-service on urban arterials: a case study in Kolkata metropolis | |
CN109598931A (en) | Group based on traffic safety risk divides and difference analysis method and system | |
CN111080158A (en) | Urban intersection traffic danger index evaluation method based on composite weight | |
CN115497306A (en) | Speed interval weight calculation method based on GIS data | |
CN111127887B (en) | Signal control optimization system and method based on real-time traffic state driving | |
CN113095387B (en) | Road risk identification method based on networking vehicle-mounted ADAS | |
CN114023065A (en) | Algorithm for intelligently diagnosing intersection service level by utilizing video analysis data | |
CN114757447B (en) | Multi-model mixed passenger transport hub station passenger flow prediction method and system | |
CN115083173B (en) | Single-point timing signal control time interval dividing method based on electric alarm data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |